Dataset Information

Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications.

ABSTRACT: Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require large computation power and processing time. In this work, we evaluate the speed-accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs. We also develop a regression model capable to estimate the performance, both in terms of processing time and accuracy. We expect this to become a very useful tool for the end user in forensic laboratories in order to estimate the performance for different face detection options. Experimental results showed that the best speed-accuracy tradeoff is achieved with images resized to 50% of the original size in GPUs and images resized to 25% of the original size in CPUs. Moreover, performance can be estimated using multiple linear regression models with a Mean Absolute Error (MAE) of 0.113, which is very promising for the forensic field.

SUBMITTER: Chaves D

PROVIDER: S-EPMC7472057 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications.

Chaves Deisy D Fidalgo Eduardo E Alegre Enrique E Alaiz-Rodríguez Rocío R Jáñez-Martino Francisco F Azzopardi George G

Sensors (Basel, Switzerland) 20200811 16

Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require large computation power and processing time. In this work, we ...[more]

PMID: 32796644

Similar Datasets

Project description:Although the identification of human skin cells is of important relevance in many forensic cases, there is currently no reliable method available. Here, we present a highly specific and sensitive messenger RNA (mRNA) approach for skin identification, meeting the key requirements in forensic analyses. We examined 11 candidate genes with skin-specific expression, as ascertained from expression databases and the literature, as well as five candidate reference genes ascertained from previous studies, in skin samples and in other forensically relevant tissues. We identified mRNA transcripts from three genes CDSN, LOR and KRT9, showing strong over-expression in skin samples relative to samples from forensic body fluids, making them suitable markers for skin identification. Out of the candidate reference genes tested, only ACTB showed similarly high expression in skin and body-fluid samples, providing a suitable reference marker for quantitative real-time PCR (qPCR) analysis of skin. Analyses of palmar and thumbprint skin samples indicate that our qPCR approach for the three skin-targeted mRNA markers, as well as the reference mRNA marker ACTB, is highly sensitive, allowing successful detection of minute amounts of skin material including full, half and quarter thumbprints, albeit with decreased success in decreasing print material. Furthermore, thumbprints stored for 6.5 months provided similar results relative to freshly analysed samples implying reasonable time-wise stability of the three skin-targeted mRNAs as well as the ACTB reference mRNA. Our study represents the first attempt towards reliable mRNA-based skin identification in forensic applications with particular relevance for future trace/touched object analyses in forensic case work. Although the approach for skin identification introduced here can be informative when applied on its own, we recommend for increased reliability the integration of (one or more of) the skin-targeted mRNA markers presented here into multiplex assays additionally including mRNA markers targeting alternative cell types expected in forensic samples.

Project description:PurposeThis work was set out to investigate the feasibility of dose reduction in SPECT myocardial perfusion imaging (MPI) without sacrificing diagnostic accuracy. A deep learning approach was proposed to synthesize full-dose images from the corresponding low-dose images at different dose reduction levels in the projection space.MethodsClinical SPECT-MPI images of 345 patients acquired on a dedicated cardiac SPECT camera in list-mode format were retrospectively employed to predict standard-dose from low-dose images at half-, quarter-, and one-eighth-dose levels. To simulate realistic low-dose projections, 50%, 25%, and 12.5% of the events were randomly selected from the list-mode data through applying binomial subsampling. A generative adversarial network was implemented to predict non-gated standard-dose SPECT images in the projection space at the different dose reduction levels. Well-established metrics, including peak signal-to-noise ratio (PSNR), root mean square error (RMSE), and structural similarity index metrics (SSIM) in addition to Pearson correlation coefficient analysis and clinical parameters derived from Cedars-Sinai software were used to quantitatively assess the predicted standard-dose images. For clinical evaluation, the quality of the predicted standard-dose images was evaluated by a nuclear medicine specialist using a seven-point (- 3 to + 3) grading scheme.ResultsThe highest PSNR (42.49 ± 2.37) and SSIM (0.99 ± 0.01) and the lowest RMSE (1.99 ± 0.63) were achieved at a half-dose level. Pearson correlation coefficients were 0.997 ± 0.001, 0.994 ± 0.003, and 0.987 ± 0.004 for the predicted standard-dose images at half-, quarter-, and one-eighth-dose levels, respectively. Using the standard-dose images as reference, the Bland-Altman plots sketched for the Cedars-Sinai selected parameters exhibited remarkably less bias and variance in the predicted standard-dose images compared with the low-dose images at all reduced dose levels. Overall, considering the clinical assessment performed by a nuclear medicine specialist, 100%, 80%, and 11% of the predicted standard-dose images were clinically acceptable at half-, quarter-, and one-eighth-dose levels, respectively.ConclusionThe noise was effectively suppressed by the proposed network, and the predicted standard-dose images were comparable to reference standard-dose images at half- and quarter-dose levels. However, recovery of the underlying signals/information in low-dose images beyond a quarter of the standard dose would not be feasible (due to very poor signal-to-noise ratio) which will adversely affect the clinical interpretation of the resulting images.

Dataset Information

Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications.

Publications

Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets